alivecat/clipseg-rd16-mnn-wq8
image-segmentation model by alivecat
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
WQ8 MNN conversion of CIDAS/clipseg-rd16 for text-guided image segmentation. Both an all-in-one model and a three-module pipeline are provided. Runtime: MNN (GitHub). All files use the RD16 architecture with decoder reduction dimension 16. Eligible weights use 8-bit quantization with block size 128. Conversion sources are the Xenova/clipseg-rd16 ONNX exports. Use an MNN runtime with batch size 1 as the documented input convention. The fp32 / fp16 filename labels identify the source conversion variants; image inputs and exported logits use float32. Run the text and vision modules first, then pass their features to the decoder using the following tensor names: The split layout allows the…
Read the full model card ↗ · Preview checked 2026-11-09T07:07:52.200Z
Inside the original model card — Document outline
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
alivecat/clipseg-rd16-mnn-wq8 is a image-segmentation model repository published by alivecat on Hugging Face. A library was not reported.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-segmentation
- Library
- Not reported
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- CLIPSegForImageSegmentation
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-11-09T06:46:51.000Z
- Last modified
- 2026-11-09T06:47:04.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: CIDAS/clipseg-rd16
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-09T06:55:49.891Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
alivecat/clipseg-rd64-refined-mnn-wq8
isaacmg/kraken-genizah-segmenter
mlboydaisuke/BiSeNet-Face-Parsing-OpenVINO